Search Results for author:
Found 64 papers, 25 papers with code
Conditional Diffusion Models with Classifier-Free Gibbs-like Guidance
In particular, contrary to common intuition, CFG does not yield samples from the target distribution associated with the limiting CFG score as the noise level approaches zero -- where the data distribution is tilted by a power $w \gt 1$ of the conditional distribution.
Online Decision-Focused Learning
Decision-focused learning (DFL) is an increasingly popular paradigm for training predictive models whose outputs are used in decision-making tasks.
Scaffold with Stochastic Gradients: New Analysis with Linear Speed-Up
This paper proposes a novel analysis for the Scaffold algorithm, a popular method for dealing with data heterogeneity in federated learning.
Detecting Benchmark Contamination Through Watermarking
Benchmark contamination poses a significant challenge to the reliability of Large Language Models (LLMs) evaluations, as it is difficult to assert whether a model has been trained on a test set.
Differential privacy guarantees of Markov chain Monte Carlo algorithms
This paper aims to provide differential privacy (DP) guarantees for Markov chain Monte Carlo (MCMC) algorithms.
A Mixture-Based Framework for Guiding Diffusion Models
Recent approaches use pre-trained diffusion models as priors to solve a wide range of such problems, only leveraging inference-time compute and thereby eliminating the need to retrain task-specific models on the same dataset.
Refined Analysis of Federated Averaging's Bias and Federated Richardson-Romberg Extrapolation
In this paper, we present a novel analysis of FedAvg with constant step size, relying on the Markov property of the underlying process.
Watermark Anything with Localized Messages
Image watermarking methods are not tailored to handle small watermarked areas.
Optimal Design for Reward Modeling in RLHF
To our knowledge, this is the first theoretical contribution in this area to provide an offline approach as well as worst-case guarantees.
Variational Diffusion Posterior Sampling with Midpoint Guidance
To tackle this issue, state-of-the-art approaches formulate the problem as that of sampling from a surrogate diffusion model targeting the posterior and decompose its scores into two terms: the prior score and an intractable guidance term.
Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson-Romberg Extrapolation
We address the problem of solving strongly convex and smooth minimization problems using stochastic gradient descent (SGD) algorithm with a constant step size.
Joint Channel Selection using FedDRL in V2X
In this paper, we study the problem of joint channel selection, where vehicles with different technologies choose one or more Access Points (APs) to transmit messages in a network.
Theoretical guarantees in KL for Diffusion Flow Matching
Flow Matching (FM) (also referred to as stochastic interpolants or rectified flows) stands out as a class of generative models that aims to bridge in finite time the target distribution $\nu^\star$ with an auxiliary distribution $\mu$, leveraging a fixed coupling $\pi$ and a bridge which can either be deterministic or stochastic.
Piecewise deterministic generative models
We introduce a novel class of generative models based on piecewise deterministic Markov processes (PDMPs), a family of non-diffusive stochastic processes consisting of deterministic motion and random jumps at random times.
Denoising Lévy Probabilistic Models
Investigating noise distribution beyond Gaussian in diffusion generative models is an open problem.
Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality
This result shows that the optimal approach for maximizing the social welfare in the presence of externality is to establish property rights, i. e., enable transfers and bargaining between the players.
Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians
In this view, VI over this specific family can be casted as the minimization of a Mollified relative entropy, i. e. the KL between the convolution (with respect to a Gaussian kernel) of an atomic measure supported on Diracs, and the target distribution.
Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priors
We present an innovative framework, divide-and-conquer posterior sampling, which leverages the inherent structure of DDMs to construct a sequence of intermediate posteriors that guide the produced samples to the target posterior.
Incentivized Learning in Principal-Agent Bandit Games
This work considers a repeated principal-agent bandit game, where the principal can only interact with her environment through the agent.
Differentially Private Representation Learning via Image Captioning
In this work, we show that effective DP representation learning can be done via image captioning and scaling up to internet-scale multimodal datasets.
Watermarking Makes Language Models Radioactive
We discover that, on the contrary, it is possible to reliably determine if a language model was trained on synthetic data if that data is output by a watermarked LLM.
Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training
We first show that the phenomenon extends to Noisy-SGD (DP-SGD without clipping), suggesting that the stochasticity (and not the clipping) is the cause of this implicit bias, even with additional isotropic Gaussian noise.
KL Convergence Guarantees for Score diffusion models under minimal data assumptions
Our study provides a rigorous analysis, yielding simple, improved and sharp convergence bounds in KL applicable to any data distribution with finite Fisher information with respect to the standard Gaussian distribution.
VITS : Variational Inference Thompson Sampling for contextual bandits
In this paper, we introduce and analyze a variant of the Thompson sampling (TS) algorithm for contextual bandits.
On the convergence of dynamic implementations of Hamiltonian Monte Carlo and No U-Turn Samplers
Under conditions similar to the ones existing for HMC, we also show that NUTS is geometrically ergodic.
Tree-Based Diffusion Schrödinger Bridge with Applications to Wasserstein Barycenters
In this paper, we consider an entropic version of mOT with a tree-structured quadratic cost, i. e., a function that can be written as a sum of pairwise cost functions between the nodes of a tree.
Non-asymptotic convergence bounds for Sinkhorn iterates and their gradients: a coupling approach
Our approach is novel in that it is purely probabilistic and relies on coupling by reflection techniques for controlled diffusions on the torus.
Rosenthal-type inequalities for linear statistics of Markov chains
In this paper, we establish novel deviation bounds for additive functionals of geometrically ergodic Markov chains similar to Rosenthal and Bernstein inequalities for sums of independent random variables.
On Sampling with Approximate Transport Maps
Transport maps can ease the sampling of distributions with non-trivial geometries by transforming them into distributions that are easier to handle.
Federated Averaging Langevin Dynamics: Toward a unified theory and new algorithms
This paper focuses on Bayesian inference in a federated learning context (FL).
Unbiased constrained sampling with Self-Concordant Barrier Hamiltonian Monte Carlo
In this paper, we propose Barrier Hamiltonian Monte Carlo (BHMC), a version of the HMC algorithm which aims at sampling from a Gibbs distribution $\pi$ on a manifold $\mathrm{M}$, endowed with a Hessian metric $\mathfrak{g}$ derived from a self-concordant barrier.
Finite-time High-probability Bounds for Polyak-Ruppert Averaged Iterates of Linear Stochastic Approximation
Our finite-time instance-dependent bounds for the averaged LSA iterates are sharp in the sense that the leading term we obtain coincides with the local asymptotic minimax limit.
Variational Inference of overparameterized Bayesian Neural Networks: a theoretical and empirical study
This paper studies the Variational Inference (VI) used for training Bayesian Neural Networks (BNN) in the overparameterized regime, i. e., when the number of neurons tends to infinity.
FedPop: A Bayesian Approach for Personalised Federated Learning
We provide non-asymptotic convergence guarantees for the proposed algorithms and illustrate their performances on various personalised federated learning tasks.
On Maximum-a-Posteriori estimation with Plug & Play priors and stochastic gradient descent
Bayesian methods to solve imaging inverse problems usually combine an explicit data likelihood function with a prior distribution that explicitly models expected properties of the solution.
NEO: Non Equilibrium Sampling on the Orbits of a Deterministic Transform
Sampling from a complex distribution $\pi$ and approximating its intractable normalizing constant $\mathrm{Z}$ are challenging problems.
Local-Global MCMC kernels: the best of both worlds
Recent works leveraging learning to enhance sampling have shown promising results, in particular by designing effective non-local moves and global proposals.
Monte Carlo Variational Auto-Encoders
Variational auto-encoders (VAE) are popular deep latent variable models which are trained by maximizing an Evidence Lower Bound (ELBO).
Fast Approximation of the Sliced-Wasserstein Distance Using Concentration of Random Projections
The Sliced-Wasserstein distance (SW) is being increasingly used in machine learning applications as an alternative to the Wasserstein distance and offers significant computational and statistical benefits.
DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within Gibbs
Performing reliable Bayesian inference on a big data scale is becoming a keystone in the modern era of machine learning.
Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize
This family of methods arises in many machine learning tasks and is used to obtain approximate solutions of a linear system $\bar{A}\theta = \bar{b}$ for which $\bar{A}$ and $\bar{b}$ can only be accessed through random estimates $\{({\bf A}_n, {\bf b}_n): n \in \mathbb{N}^*\}$.
QLSD: Quantised Langevin stochastic dynamics for Bayesian federated learning
The objective of Federated Learning (FL) is to perform statistical inference for data which are decentralised and stored locally on networked clients.
NEO: Non Equilibrium Sampling on the Orbit of a Deterministic Transform
Sampling from a complex distribution $\pi$ and approximating its intractable normalizing constant Z are challenging problems.
Bayesian imaging using Plug & Play priors: when Langevin meets Tweedie
The proposed algorithms are demonstrated on several canonical problems such as image deblurring, inpainting, and denoising, where they are used for point estimation as well as for uncertainty visualisation and quantification.
On Riemannian Stochastic Approximation Schemes with Fixed Step-Size
This result gives rise to a family of stationary distributions indexed by the step-size, which is further shown to converge to a Dirac measure, concentrated at the solution of the problem at hand, as the step-size goes to 0.
On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning
This paper studies the exponential stability of random matrix products driven by a general (possibly unbounded) state space Markov chain.
Nonreversible MCMC from conditional invertible transforms: a complete recipe with convergence guarantees
This paper fills the gap by developing general tools to ensure that a class of nonreversible Markov kernels, possibly relying on complex transforms, has the desired invariance property and leads to convergent algorithms.
Quantitative Propagation of Chaos for SGD in Wide Neural Networks
In comparison to previous works on the subject, we consider settings in which the sequence of stepsizes in SGD can potentially depend on the number of neurons and the iterations.
Convergence Analysis of Riemannian Stochastic Approximation Schemes
This paper analyzes the convergence for a large class of Riemannian stochastic approximation (SA) schemes, which aim at tackling stochastic optimization problems.
Convergence rates and approximation results for SGD and its continuous-time counterpart
This paper proposes a thorough theoretical analysis of Stochastic Gradient Descent (SGD) with non-increasing step sizes.
Statistical and Topological Properties of Sliced Probability Divergences
The idea of slicing divergences has been proven to be successful when comparing two probability measures in various machine learning applications including generative modeling, and consists in computing the expected value of a `base divergence' between one-dimensional random projections of the two measures.
MetFlow: A New Efficient Method for Bridging the Gap between Markov Chain Monte Carlo and Variational Inference
In this contribution, we propose a new computationally efficient method to combine Variational Inference (VI) with Markov Chain Monte Carlo (MCMC).
Maximum entropy methods for texture synthesis: theory and practice
Recent years have seen the rise of convolutional neural network techniques in exemplar-based image synthesis.
Maximum likelihood estimation of regularisation parameters in high-dimensional inverse problems: an empirical Bayesian approach. Part I: Methodology and Experiments
In this work, we propose a general empirical Bayesian method for setting regularisation parameters in imaging problems that are convex w. r. t.
Methodology Computation 62C12, 65C40, 68U10, 62F15, 65J20, 65C60, 65J22
Approximate Bayesian Computation with the Sliced-Wasserstein Distance
Approximate Bayesian Computation (ABC) is a popular method for approximate inference in generative models with intractable but easy-to-sample likelihood.
Markov Decision Process for MOOC users behavioral inference
Studies on massive open online courses (MOOCs) users discuss the existence of typical profiles and their impact on the learning process of the students.
Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance
Minimum expected distance estimation (MEDE) algorithms have been widely used for probabilistic models with intractable likelihood functions and they have become increasingly popular due to their use in implicit generative modeling (e. g. Wasserstein generative adversarial networks, Wasserstein autoencoders).
Copula-like Variational Inference
This family is based on new copula-like densities on the hypercube with non-uniform marginals which can be sampled efficiently, i. e. with a complexity linear in the dimension of state space.
The promises and pitfalls of Stochastic Gradient Langevin Dynamics
As $N$ becomes large, we show that the SGLD algorithm has an invariant probability measure which significantly departs from the target posterior and behaves like Stochastic Gradient Descent (SGD).
Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions
To the best of our knowledge, the proposed algorithm is the first nonparametric IGM algorithm with explicit theoretical guarantees.
Analysis of Langevin Monte Carlo via convex optimization
In this paper, we provide new insights on the Unadjusted Langevin Algorithm.
Bridging the Gap between Constant Step Size Stochastic Gradient Descent and Markov Chains
We consider the minimization of an objective function given access to unbiased estimates of its gradient through stochastic gradient descent (SGD) with constant step-size.
Stochastic Gradient Richardson-Romberg Markov Chain Monte Carlo
We illustrate our framework on the popular Stochastic Gradient Langevin Dynamics (SGLD) algorithm and propose a novel SG-MCMC algorithm referred to as Stochastic Gradient Richardson-Romberg Langevin Dynamics (SGRRLD).
High-dimensional Bayesian inference via the Unadjusted Langevin Algorithm
We consider in this paper the problem of sampling a high-dimensional probability distribution $\pi$ having a density with respect to the Lebesgue measure on $\mathbb{R}^d$, known up to a normalization constant $x \mapsto \pi(x)= \mathrm{e}^{-U(x)}/\int_{\mathbb{R}^d} \mathrm{e}^{-U(y)} \mathrm{d} y$.
